Tweetovi

Blokirali ste korisnika/cu @yanaiela

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @yanaiela

  1. Prikvačeni tweet
    26. kol 2019.

    After a lot of work, I'm very happy to see this project integrated in the best library for

    Poništi
  2. 30. sij
    Poništi
  3. 20. sij

    אני מעביר היום הרצאה במיטאפ של דאטהאק על איך לייצר התפלגויות של תכונות מדידות (למשל משקל, זמן) למילים. בואו!

    Poništi
  4. proslijedio/la je Tweet
    14. sij

    All other illustrations of samples relative to the population are dead to me. This is the one true way.

    Poništi
  5. proslijedio/la je Tweet
    1. sij

    We present our new year special: “oLMpics - On what Language Model pre-training captures״, , Exploring what symbolic reasoning skills are learned from an LM objective. We introduce 8 oLMpic games and controls for disentangling pre-training from fine-tuning.

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    1. pro 2019.

    Dear NLPeople! Do you know anyone working on Sign Language Processing? Please send me their info!

    Poništi
  7. 28. stu 2019.

    Do turkers work on Turkey Day?

    Poništi
  8. 7. stu 2019.

    Thanks with a really nice live tweet summary of my talk

    Poništi
  9. 6. stu 2019.
    Prikaži ovu nit
    Poništi
  10. 6. stu 2019.
    Prikaži ovu nit
    Poništi
  11. 6. stu 2019.
    Prikaži ovu nit
    Poništi
  12. 6. stu 2019.

    Did your numbers lose their heads?! Come to my talk tomorrow to find out how to recover them. Tomorrow (7/11) at 17:06 at the lexical semantics session @emnlp2019 shared work with , published this year at TACL

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    4. stu 2019.

    If you happen to attend , you are welcome to my talk on our paper "Transfer Learning Between Related Tasks Using Expected Label Proportions", joint work with , tomorrow at 11:40, Machine Learning session, hall 2c @emnlp2019

    Prikaži ovu nit
    Poništi
  14. 3. stu 2019.
    Poništi
  15. proslijedio/la je Tweet
    31. lis 2019.

    Please check out my new post: "The Problem of Faithfulness in (Neural Network) NLP Interpretations" on Medium! Despite how important this problem is, it's hard to separate it from general interpretability in literature. 1/

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    27. lis 2019.

    BIU NLP is huge! First group meeting of the year. Another ~15 (!) people are not even in the picture.

    Poništi
  17. proslijedio/la je Tweet
    11. lis 2019.

    Now Reut Tsarfaty presents "The Empty Elements Project: Reading Beyond the Text and Between the Lines" at

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet

    Stoked to share this paper: We leverage MTurkers not to label but to revise documents to accord with ***counterfactual labels***. Resulting data enables us to disentangle “the difference that makes the difference”. Herculean effort by (1/n)

    Prikaži ovu nit
    Poništi
  19. 24. ruj 2019.

    a computer scientist dilemma in the piano playing domain: counting fingers from 0 to 4, or from 1 to 5?

    Poništi
  20. proslijedio/la je Tweet
    16. kol 2019.

    Clever Hans: the horse we thought could do arithmetic, but really was relying on other signals. Really enjoyed this blog post on NLP, clever hands and what to do instead of leaderboards.

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·